Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Auto Scaling is a service designed to dynamically adjust computing resources in response to fluctuations in user demand. When there is an uptick in requests, it seamlessly adds ECS instances to accommodate the increased load, while conversely, it reduces the number of instances during quieter times to optimize resource allocation. This service not only adjusts resources automatically based on predefined scaling policies but also allows for manual intervention through scale-in and scale-out options, giving you the flexibility to manage resources as needed. During high-demand periods, it efficiently expands the available computing resources, ensuring optimal performance, and when demand wanes, Auto Scaling efficiently retracts ECS resources, helping to minimize operational costs. Additionally, this adaptability ensures that your system remains responsive and cost-effective throughout varying usage patterns.
Description
NVIDIA DGX Cloud Serverless Inference provides a cutting-edge, serverless AI inference framework designed to expedite AI advancements through automatic scaling, efficient GPU resource management, multi-cloud adaptability, and effortless scalability. This solution enables users to reduce instances to zero during idle times, thereby optimizing resource use and lowering expenses. Importantly, there are no additional charges incurred for cold-boot startup durations, as the system is engineered to keep these times to a minimum. The service is driven by NVIDIA Cloud Functions (NVCF), which includes extensive observability capabilities, allowing users to integrate their choice of monitoring tools, such as Splunk, for detailed visibility into their AI operations. Furthermore, NVCF supports versatile deployment methods for NIM microservices, granting the ability to utilize custom containers, models, and Helm charts, thus catering to diverse deployment preferences and enhancing user flexibility. This combination of features positions NVIDIA DGX Cloud Serverless Inference as a powerful tool for organizations seeking to optimize their AI inference processes.
API Access
Has API
No
API Access
Has API
Yes
Integrations
Amazon Web Services (AWS)
No
CoreWeave
No
F5 Distributed Cloud DDoS Mitigation Service
Yes
Google Cloud Platform
No
Helm
No
Llama
No
Microsoft Azure
No
NVIDIA AI Foundations
No
NVIDIA Cloud Functions
No
NVIDIA DGX Cloud
No
Integrations
Amazon Web Services (AWS)
Yes
CoreWeave
Yes
F5 Distributed Cloud DDoS Mitigation Service
No
Google Cloud Platform
Yes
Helm
Yes
Llama
Yes
Microsoft Azure
Yes
NVIDIA AI Foundations
Yes
NVIDIA Cloud Functions
Yes
NVIDIA DGX Cloud
Yes
Pricing Details
This service is available free of charge. You will be only charged for the standard cost of adding additional ECS resources.
Free Trial
No
Free Version
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Deployment
Web-Based
No
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
No
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
Yes
In Person
Yes
Vendor Details
Company Name
Alibaba Cloud
Founded
2009
Country
China
Website
www.alibabacloud.com/product/auto-scaling
Vendor Details
Company Name
NVIDIA
Founded
1993
Country
United States
Website
developer.nvidia.com/dgx-cloud/serverless-inference
Product Features
Server Virtualization
Audit Management
Yes
Health Monitoring
Yes
Live Machine Migration
No
Multi-OS Virtual Machines
No
Patching / Backup
No
Performance Log
Yes
Performance Optimization
Yes
Rapid Provisioning
Yes
Security Management
No
Type 1 / Type 2 Hypervisor
No